🛡️ AI Infrastructure Security Assessment System

中文版

AI Infra Guard is an efficient, lightweight, and user-friendly AI infrastructure security assessment tool designed to discover and detect potential security risks in AI systems.

🚀 Project Highlights

• Efficient Scanning* Supports 28 AI framework fingerprint identifications

  • Covers 200+ security vulnerability databases

• Easy to Use

  • Ready to use out of the box, no complex configuration
  • Fingerprint and vulnerability YAML rule definitions
  • Flexible matching syntax

• Lightweight

  • Clean and efficient core components
  • Small binary size, low resource usage
  • Cross-platform support

📊 AI Component Coverage

Component Name	Vulnerability Count
anythingllm	8
langchain	21
Chuanhugpt	0
comfy_mtb	1
ComfyUI-Prompt-Preview	1
ComfyUI-Custom-Scripts	1
comfyui	2
dify	0
fastchat-webui	0
fastchat	0
feast	0
gradio	41
jupyterlab	4
jupyter-notebook	1
jupyter-server	7
kubeflow	4
kubepi	5
llamafactory	1
ollama	5
open-webui	1
pyload-ng	18
qanything	2
ragflow	1
ray	3
tensorboard	0
vllm	3
xinference	0

🚀 Quick Preview

Quick Usage

AI Analysis

📦 Installation and Usage

Installation

Download from: https://github.com/Tencent/AI-Infra-Guard/releases

Usage

Single Target

./ai-infra-guard -target [IP/Domain] 

Multiple Targets

./ai-infra-guard -target [IP/Domain] -target [IP/Domain]

Read from File

./ai-infra-guard -file target.txt

AI Analysis

./ai-infra-guard -target [IP/Domain] -ai -token [Hunyuan token]

🔍 Fingerprint Matching Rules

AI Infra Guard is based on WEB fingerprint identification components. Fingerprint rules are in the data/fingerprints directory, and vulnerability matching rules are in the data/vuln directory.

Example: Gradio Fingerprint Rule

info:
  name: gradio
  author: Security Team
  severity: info
  metadata:
    product: gradio
    vendor: gradio
http:
  - method: GET
    path: '/'
    matchers:
      - body="<script>window.gradio_config = {" || body="document.getElementsByTagName(\"gradio-app\");"

🛠️ Fingerprint Matching Syntax

Matching Locations

• Title
• Body
• Header
• Icon hash

Logical Operators

• = Fuzzy match
• == Exact match
• != Not equal
• ~= Regular expression match
• && AND
• || OR
• () Grouping

🤝 Contributing

Community contributions are highly welcome! Feel free to submit PRs and Issues.

📄 License

"AI Infra Guard" is licensed under the MIT License except for the third-party components. Visit License.txt

---

💡 Tip: Stay updated to protect your AI infrastructure security!